What are the hardware requirements for Qwen3 5 35B A3b Oc 200K Rl?

Qwen3 5 35B A3b Oc 200K Rl requires approximately 71.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3 5 35B A3b Oc 200K Rl and how large is it?

Qwen3 5 35B A3b Oc 200K Rl is developed by Lego-X, a model with 35b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Qwen3 5 35B A3b Oc 200K Rl?

Qwen3 5 35B A3b Oc 200K Rl is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3 5 35B A3b Oc 200K Rl by Lego-X — VRAM 71.9GB

Name: Qwen3 5 35B A3b Oc 200K Rl
Author: Lego-X

Qwen3 5 35B A3b Oc 200K Rl is an open-source language model by Lego-X. Features: 35b LLM, VRAM: 71.9GB, License: apache-2.0, LLM Explorer Score: 0.32.

Arxiv:2608.17393 Agentic Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-35b-a3... Code Coding-agent Conversational Dataset:lego-x/lego-rl-2699 En Endpoints compatible Gspo Image-text-to-text Moe Opencode Qwen3 5 moe Region:us Safetensors Sharded Swe-bench Tensorflow

Model Card on HF 🤗: https://huggingface.co/Lego-X/qwen3_5_35b_a3b_oc_200k_rl

Qwen3 5 35B A3b Oc 200K Rl Parameters and Internals

LLM Name	Qwen3 5 35b A3b Oc 200k Rl
Repository 🤗	https://huggingface.co/Lego-X/qwen3_5_35b_a3b_oc_200k_rl
Base Model(s)	Qwen/Qwen3.5-35B-A3B Qwen/Qwen3.5-35B-A3B
Model Size	35b
Required VRAM	71.9 GB
Updated	2026-08-27
Maintainer	Lego-X
Model Type	qwen3_5_moe
Model Files	42.5 GB: 1-of-2 29.4 GB: 2-of-2
Supported Languages	en
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	5.4.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Qwen3 5 35B A3b Oc 200K Rl capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Qwen3 5 35B A3b Oc 200K Rl

Best Alternatives	Context / RAM	Downloads	Likes
Ornith 1.5 35B A3B NPU2	256K / GB	118	1
Qwen3.6 35B A3B	0K / 72.2 GB	5540855	2648
Qwen3.5 35B A3B	0K / 72.3 GB	2158511	1482
Ornith 1.0 35B	0K / 70.4 GB	3127649	503
Qwen3.6 35B A3B NVFP4	0K / 23.4 GB	8788684	482
KAT Coder V2.5 Dev	0K / 69.7 GB	17885	537
Qwen3.6 35B A3B FP8	0K / 0.8 GB	8984811	343
Ornith 1.5 35B A3B	0K / 72.1 GB	1713	201
Qwen AgentWorld 35B A3B	0K / 69.2 GB	66155	665
Qwen3.6 35B A3B NVFP4 Fast	0K / 23.6 GB	463661	98

Note: green Score (e.g. "73.2") means that the model is better than Lego-X/qwen3_5_35b_a3b_oc_200k_rl.